INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RectangleBorder

-0.48

expandindo

-0.47

พล

-0.44

estival

-0.43

setVerticalGroup

-0.43

 TextAppearance

-0.43

 laſt

-0.43

ACHUSET

-0.42

imanapun

-0.42

Becky

-0.42

POSITIVE LOGITS

المكان

0.53

 للاسماء

0.52

 ligiloj

0.49

rungsseite

0.48

 esternos

0.48

ագրություններ

0.43

WebServlet

0.42

homonymie

0.42

SourceChecksum

0.39

請繼續往下閱讀

0.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.